記述言語：日本語   出版者・発行元：一般社団法人 システム制御情報学会  

DOI： 10.11509/isciesci.66.4_115

CiNii Research

記述言語：英語   出版者・発行元：Current Biology  

Mutations in the tumor-suppressor Hippo pathway lead to activation of the transcriptional coactivator Yorkie (Yki), which enhances cell proliferation autonomously and causes cell death non-autonomously. While Yki-induced cell proliferation has extensively been studied, the mechanism by which Yki causes cell death in nearby wild-type cells, a phenomenon called supercompetition, and its role in tumorigenesis remained unknown. Here, we show that Yki-induced supercompetition is essential for tumorigenesis and is driven by non-autonomous induction of autophagy. Clones of cells mutant for a Hippo pathway component fat activate Yki and cause autonomous tumorigenesis and non-autonomous cell death in Drosophila eye-antennal discs. Through a genetic screen in Drosophila, we find that mutations in autophagy-related genes or NF-κB genes in surrounding wild-type cells block both fat-induced tumorigenesis and supercompetition. Mechanistically, fat mutant cells upregulate Yki-target microRNA bantam, which elevates protein synthesis levels via activation of TOR signaling. This induces elevation of autophagy in neighboring wild-type cells, which leads to downregulation of IκB Cactus and thus causes NF-κB-mediated induction of the cell death gene hid. Crucially, upregulation of bantam is sufficient to make cells to be supercompetitors and downregulation of endogenous bantam is sufficient for cells to become losers of cell competition. Our data indicate that cells with elevated Yki-bantam signaling cause tumorigenesis by non-autonomous induction of autophagy that kills neighboring wild-type cells.

DOI： 10.1016/j.cub.2022.01.016

Web of Science

Scopus

PubMed

記述言語：日本語   出版者・発行元：一般社団法人 日本機械学会  

DOI： 10.1299/jsmermd.2022.2a2-l05

CiNii Research

記述言語：日本語   出版者・発行元：一般社団法人 日本機械学会  

DOI： 10.1299/jsmermd.2022.1p1-g05

CiNii Research

記述言語：日本語   出版者・発行元：自動制御連合講演会  

DOI： 10.11511/jacc.65.0_1483

CiNii Research

記述言語：日本語   出版者・発行元：一般社団法人 日本ロボット学会  

DOI： 10.7210/jrsj.40.437

CiNii Research

記述言語：日本語   出版者・発行元：一般社団法人 日本機械学会  

DOI： 10.1299/jsmermd.2022.2p1-h02

CiNii Research

記述言語：日本語   出版者・発行元：一般社団法人 日本ロボット学会  

DOI： 10.7210/jrsj.40.879

CiNii Research

記述言語：日本語   出版者・発行元：一般社団法人 日本ロボット学会  

<p></p>

DOI： 10.7210/jrsj.39.526

CiNii Research

記述言語：日本語   出版者・発行元：一般社団法人 日本機械学会  

DOI： 10.1299/jsmermd.2021.1a1-g03

CiNii Research

記述言語：日本語   出版者・発行元：一般社団法人 日本機械学会  

DOI： 10.1299/jsmermd.2021.1p1-l15

CiNii Research

記述言語：日本語   出版者・発行元：一般社団法人 日本機械学会  

DOI： 10.1299/jsmemovic.2021.17.b20

CiNii Research

記述言語：日本語  

Web of Science

記述言語：日本語  

Web of Science

記述言語：日本語  

Web of Science

記述言語：日本語  

Web of Science

記述言語：日本語   出版者・発行元：公益社団法人 計測自動制御学会  

DOI： 10.9746/sicetr.55.745

CiNii Research

記述言語：日本語   出版者・発行元：公益社団法人 自動車技術会  

自車両位置認識は自動運転における基幹技術であり，位置認識の失敗は自動運転自体の失敗へ直結する危険がある．しかし，その認識結果の正誤を保証する術はない．本稿では，位置認識の正誤を学習した学習機の出力を新たな観測変数として利用し，ロバストに位置認識結果の正誤（信頼度）を推定するモデルを提案・検証する．

DOI： 10.11351/jsaeronbun.50.609

CiNii Research

記述言語：日本語   出版者・発行元：公益社団法人 自動車技術会  

自動運転を行うためには，走行すべき経路との相対位置関係や，注視すべき物体の情報を得ることが有用であり，そのためにも，自己位置推定は重要な技術である．本稿では，デッドレコニングとマルチレイヤーLIDARによる位置推定結果を融合することで，一般道における高精度位置推定，および自動運転を達成したので報告する．

DOI： 10.11351/jsaeronbun.49.675

CiNii Research

記述言語：日本語   出版者・発行元：一般社団法人 日本ロボット学会  

DOI： 10.7210/jrsj.34.397

CiNii Research

記述言語：日本語   出版者・発行元：[出版社不明]  

自動車と歩行者が交差するシーンに着目し，車両歩行者間のインタラクティブな行動をモデル化するための2段階入出力隠れマルコフモデル（TS-IOHMM）を提案する．従来の入出力隠れマルコフモデルは，相手の行動に依存して自己の意図と行動が決定される過程をモデル化した．提案するTS-IOHMMは，相手の行動の影響に加え，自己の行動もまた相手の意図に影響を与える点を考慮したモデルで，これまで注目されなかった意図と行動の変化にある法則性（ルール）の獲得を目指したモデルである．検証用に設定したルールに従って意図や行動が変化するシミュレーションデータを作成し，それを用いて提案モデルがどのようなルールを獲得できるか検証する実験を行った．その結果から，提案モデルがシミュレーションと同等の意図や行動を出力する行動ルールを獲得できたことを確認した．
This paper presents the Two-Stage Input-Output Hidden Markov Model (TS-IOHMM) which is a modeling method for interactive behavior between a car and a pedestrian focusing on the scene where the car and the pedestrian intersect. The conventional Input-Ouput Hidden Markov Model (IOHMM) models the process that the driver's intention and behavior are determined depending on the behavior of the pedestrian. The proposed TS-IOHMM is a model that considers not only the influence of the pedestrian's behavior, but also that the driver's behavior affects the pedestrian intention. In this paper, we aim to acquire a rule in the change of the driver's intentions and behaviors by the proposed model. We generated simulation data in which the driver's intentions and behaviors change according to a certain rule, and conducted experiments to evaluate that the proposed model was able to correctly provide intentions and behaviors equivalent to those according to the rule.

DOI： 10.20729/00218987

CiNii Books

記述言語：英語   掲載種別：研究論文（学術雑誌）   出版者・発行元：IEEE Robotics and Automation Letters  

This letter presents a mobile robot localization method that uses depth regression from camera images. In this work, we use convolutional neural networks to regress the depth from the camera images. However, the depth regression results contain uncertainty, which must be resolved to stably perform localization with the depth regression results. This letter proposes a novel probabilistic model that enables the handling of the uncertainty of the depth regression results while localizing the robot pose. By handling the uncertainty, inaccurate depth regression results can be ignored, and localization robustness can be increased. We compare the proposed method with two traditional methods used in particle-filter-based localization that do not handle depth regression uncertainty. Comparison experiments are performed using two types of datasets: a manually created dataset using only a visual inertial odometry sensor, and the KITTI odometry dataset. Results show that the proposed method can track the robot pose even though the depth regression results are inaccurate and can increase localization accuracy without increasing memory and computational costs.

DOI： 10.1109/LRA.2021.3140062

Web of Science

Scopus

掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：2022 IEEE/SICE International Symposium on System Integration, SII 2022  

Recently, many researchers in the mobile robot field study how to realize socially-aware navigation in human-robot coexisting spaces. However, we have fundamental questions: how can be the socially-aware behavior defined and classified? Our work aims to provide the answers and is divided into two major studies; defining the socially-aware behavior in terms of the traffic psychology and extracting specific patterns to understand the behavior. For the first study, we designed simulation experiments based on the traffic psychology. In the experiments, participants operated an ego-agent to a destination with three different instructions; cooperative, urgent, and non-urgent. We also analyzed differences of the navigation styles and found that the statistical trend of the ego-motion is different in each style. However, it is difficult to find specific patterns in relation between the ego-motion and surrounding situations. This paper focuses on the second study and presents a classification method of the navigation styles using persistent homology (PH). We consider that implicit patterns could be extracted from surrounding situations by PH because it could enable to find specific patterns from data even when they seem to be distributed randomly. Results show the possibility that the PH-based method could acquire effective information for the classification.

DOI： 10.1109/SII52469.2022.9708804

Web of Science

Scopus

その他リンク： https://dblp.uni-trier.de/db/conf/sii/sii2022.html#AkaiMMHM22

掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：2022 IEEE/SICE International Symposium on System Integration, SII 2022  

Visual localization is typically implemented using optimization algorithms. Because the optimization minimizes a cost function, their estimate is sensitive to noises, and estimated trajectory is usually jerk. The estimate can be fused with other estimates using Bayesian filter (BF) and smooth trajectory can be obtained; however, the optimization-based localization does not estimate uncertainty. In this study, we present an uncertainty estimation method for the optimization-based localization using Hessian matrix. The Hessian matrix is used in Newton method to calculate the increment. The increment is obtained by multiplying the inverse of Hessian and the gradient of the cost function. We consider that the inverse of Hessian could be used to indicate variability of the optimized states, and determine the uncertainty. We determine normal distribution over the estimate by the optimization-based localization and its uncertainty, that is, covariance, is determined using Hessian. In the experiment, we validate the uncertainty estimation method under different measurement conditions, and the effectiveness of the fusion using BF. Results show that the uncertainty can be appropriately estimated according to the conditions, and smooth trajectory can be estimated while maintaining the tracking accuracy to the visual localization result. Furthermore, we conduct autonomous flight navigation experiment with a quadcopter based on the presented localization, and its navigation is successfully performed. The software used in this work is publicly available.

DOI： 10.1109/SII52469.2022.9708767

Web of Science

Scopus

その他リンク： https://dblp.uni-trier.de/db/conf/sii/sii2022.html#AkaiYASTH22

掲載種別：研究論文（学術雑誌）   出版者・発行元：IEEE Transactions on Intelligent Transportation Systems  

Most of the recent automated driving systems assume the accurate functioning of localization. Unanticipated errors cause localization failures and result in failures in automated driving. An exact localization failure detection is necessary to ensure safety in automated driving; however, detection of the localization failures is challenging because sensor measurement is assumed to be independent of each other in the localization process. Owing to the assumption, the entire relation of the sensor measurement is ignored. Consequently, it is difficult to recognize the misalignment between the sensor measurement and the map when partial sensor measurement overlaps with the map. This paper proposes a method for the detection of localization failures using Markov random fields with fully connected latent variables. The full connection enables to take the entire relation into account and contributes to the exact misalignment recognition. Additionally, this paper presents localization failure probability calculation and efficient distance field representation methods. We evaluate the proposed method using two types of datasets. The first dataset is the SemanticKITTI dataset, whereby four methods are compared with the proposed method. The comparison results reveal that the proposed method achieves the most accurate failure detection. The second dataset is created based on log data acquired from the demonstrations that we conducted in Japanese public roads. The dataset includes several localization failure scenes. We apply the failure detection methods to the dataset and confirm that the proposed method achieves exact and immediate failure detection.

DOI： 10.1109/tits.2022.3164397

Web of Science

Scopus

記述言語：英語   掲載種別：研究論文（学術雑誌）   出版者・発行元：IEEJ Transactions on Electrical and Electronic Engineering  

The main stream of development of autonomous driving technology (ADT) is for four-wheel motor vehicles. ADT for motorcycles has received scant attention. The motorcycle stability tends to diminish when being driven at extremely low speed. This study addresses how a motorcycle should be stabilized under low-speed driving. To obtain a linearized motorcycle model without skidding, we introduce a model based on SPACAR, a finite element method computation program. Moreover, velocity-dependent gain-scheduling linear quadratic regulator (LQR) is applied. The experimental results demonstrate stabilized driving responses at 1.5 km/h, which is slower than a person's typical walking speed. © 2021 Institute of Electrical Engineers of Japan. Published by Wiley Periodicals LLC.

DOI： 10.1002/tee.23550

Web of Science

Scopus

記述言語：英語   掲載種別：研究論文（学術雑誌）   出版者・発行元：Neural Networks  

We investigate classification performance of neural networks (NNs) based on topological insight in an attempt to guarantee stability of their inference. NNs which can accurately classify a dataset map it into a hidden space while disentangling intertwined data. NNs sometimes acquire forcible mapping to disentangle the data, and this forcible mapping generates outliers. The mapping around the outliers is unstable because the outputs change drastically. Hence, we define stable NNs to mean that they do not generate outliers. To investigate the possibility of the existence of outliers, we use persistent homology and a method to estimate the confidence set for persistence diagrams. The combined use enables us to test whether the focused geometry is topologically simple, that is, no outliers. In this work, we use the MNIST and CIFAR-10 datasets and investigate the relationship between the classification performance and the topological characteristics with several NNs. Investigation results with the MNIST dataset show that the test accuracy of all the networks is superior, exceeding 98%, even though the transformed dataset is not topologically simple. Results with the CIFAR-10 dataset also show that the possibility of the existence of outliers is shown in the mapping by the accurate convolutional NNs. Therefore, we conclude that the presented investigation is necessary to guarantee that the NNs, in particular deep NNs, do not acquire unstable mapping for forcible classification.

DOI： 10.1016/j.neunet.2021.05.007

Web of Science

Scopus

PubMed

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：IEEE Intelligent Vehicles Symposium, Proceedings  

Recently, various applications leveraging topological data analysis, in particular, persistent homology (PH), have been presented in many fields since PH provides a novel point cloud analysis method. In this work, we apply PH to LiDAR-based ego-vehicle localization applications. PH can extract translation and rotation invariant features from a point cloud. These features do not maintain local information of the point cloud, such as the edges and lines; however, they can abstract the global structure of the point cloud. A persistence image (PI) vectorizes the features and allows us to obtain fixed-size vectors despite the sizes of the source point clouds being different. Additionally, the size of the PI is not large even though the source point cloud is extremely big. We consider that these advantages are effective to loop closure detection, place categorization, and end-to-end global localization applications. Results reveal that it is difficult to improve the localization accuracy by simply applying PH owing to the basic concept of the topology that does not focus on exact shapes of the geometry. Therefore, we discuss how the advantages of PH can be utilized for the localization.

DOI： 10.1109/IV48863.2021.9575312

Web of Science

Scopus

その他リンク： https://dblp.uni-trier.de/db/conf/ivs/ivs2021.html#AkaiHM21

記述言語：日本語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：2020 IEEE 23rd International Conference on Intelligent Transportation Systems, ITSC 2020  

It is intuitively obvious that eye-gaze behaviors of experienced drivers are different from those of novice drivers. However, it is not easy to understand the difference in their behavior quantitatively. In this work, we present an explainable eye-gaze behavior modeling method for electric wheelchair drivers based on Inverse Reinforcement Learning (IRL). We first create feature maps that represent risk factors during driving. These feature maps are able to represent not only to what but also from where drivers pay attention. IRL uses the feature maps to learn the reward representing the eyegaze behaviors and allows us to see important features via the automatic acquisition of the reward. Through analysis of the learned model, we show quantitative evidence that eye-gaze behaviors of experienced drivers are better-balanced by paying attention to multiple risks.

DOI： 10.1109/ITSC45102.2020.9294255

Scopus

その他リンク： https://dblp.uni-trier.de/db/conf/itsc/itsc2020.html#MaekawaAHMDKIM20

記述言語：英語   掲載種別：研究論文（学術雑誌）   出版者・発行元：IEEE Transactions on Vehicular Technology  

This paper introduces a method to extract driving behaviors from a human expert driver which are applied to an autonomous agent to reproduce proactive driving behaviors. Deep learning techniques were used to extract latent features from the collected data. Extracted features were clustered into behaviors and used to create velocity profiles allowing an autonomous driving agent could drive in a human-like manner. By using proactive driving behaviors, the agent could limit potential sources of discomfort such as jerk and uncomfortable velocities. Additionally, we proposed a method to compare trajectories where not only the geometric similarity is considered, but also velocity, acceleration and jerk. Experimental results in a simulator implemented in ROS show that the autonomous agent built with the driving behaviors was capable of driving similarly to expert human drivers.

DOI： 10.1109/TVT.2020.2980197

Web of Science

Scopus

記述言語：英語   掲載種別：研究論文（学術雑誌）   出版者・発行元：IEEE Robotics and Automation Letters  

Semantics can be leveraged in ego-vehicle localization to improve robustness and accuracy because objects with the same labels can be correctly matched with each other. Object recognition has significantly improved owing to advances in machine learning algorithms. However, perfect object recognition is still challenging in real environments. Hence, the uncertainty of object recognition must be considered in localization. This letter proposes a novel localization method that integrates a supervised object recognition method, which predicts probabilistic distributions over object classes for individual sensor measurements, into the Bayesian network for localization. The proposed method uses the estimated probabilities and Dirichlet distribution to calculate the likelihood for estimating an ego-vehicle pose. Consequently, the uncertainty can be handled in localization. We present an implementation example of the proposed method using a particle filter and deep-neural-network-based point cloud semantic segmentation and evaluate it by simulation and the SemanticKITTI dataset. Experimental results show that the proposed method can accurately generate likelihood distribution even when object recognition accuracy is degraded, and its estimation accuracy is the highest compared to that of two conventional methods.

DOI： 10.1109/LRA.2020.2998403

Web of Science

Scopus

記述言語：日本語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：Proceedings - IEEE International Conference on Robotics and Automation  

This paper proposes a hybrid localization method that fuses Monte Carlo localization (MCL) and convolutional neural network (CNN)-based end-to-end (E2E) localization. MCL is based on particle filter and requires proposal distributions to sample the particles. The proposal distribution is generally predicted using a motion model. However, because the motion model cannot handle unanticipated errors, the predicted distribution is sometimes inaccurate. The use of other ideal proposal distributions, such as the measurement model, can improve robustness against such unanticipated errors. This technique is called importance sampling (IS). However, it is difficult to sample the particles from such ideal distributions because they are not represented in the closed form. Recent works have proved that CNNs with dropout layers represent the posterior distributions over their outputs conditioned on the inputs and the CNN predictions are equivalent to sampling the outputs from the posterior. Therefore, the proposed method utilizes a CNN to sample the particles and fuses them with MCL via IS. Consequently, the advantages of both MCL and E2E localization can be simultaneously leveraged while preventing their disadvantages. Experiments demonstrate that the proposed method can smoothly estimate the robot pose, similar to the model-based method, and quickly re-localize it from the failures, similar to the learning-based method.

DOI： 10.1109/ICRA40945.2020.9196568

Scopus

その他リンク： https://dblp.uni-trier.de/db/conf/icra/icra2020.html#AkaiHM20

記述言語：日本語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：IEEE Intelligent Vehicles Symposium, Proceedings  

This paper presents a LiDAR-based 3D Monte Carlo localization (MCL) with an efficient distance field (DF) representation method. To implement 3D MCL, high computing capacity is required because the likelihood of many pose candidates, i.e., particles, must be calculated in real time by comparing sensor measurements and a map. Additionally, a large-scale map is needed for allocation to embedded computers since autonomous vehicles are required to navigate wide areas. These make it difficult for 3D MCL implementation. This paper first presents an efficient DF representation method while considering the 3D LiDAR-based localization characteristics. Because each DF voxel has the closest distance from occupied voxels, swift comparison of the sensor measurements and map can be achieved. Consequently, 3D MCL using the likelihood field model (LFM) can be executed in real time. Furthermore, this paper presents a method for improving the localization robustness to environmental changes without increasing memory and computational cost from that of the LFM-based MCL. Through experiments using the SemanticKITTI dataset, we show that the presented method can efficiently and robustly work in dynamic environments.

DOI： 10.1109/IV47402.2020.9304679

Scopus

その他リンク： https://dblp.uni-trier.de/db/conf/ivs/ivs2020.html#AkaiHM20

記述言語：日本語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：IEEE Intelligent Vehicles Symposium, Proceedings  

Interaction detection between vehicles and vulnerable road users (e.g. pedestrians and cyclists) is important for e.g. safety control and autonomous driving. However, there are many challenges for automatically detecting interactions, such as the ambiguity of defining when interaction is required in dynamic traffic activities among different road users and the lack of labeled data for training a machine learning detector. To overcome the challenges, we introduce a way to define whether or not interaction is required in various traffic scenes and create a large real-world dataset from a very challenging intersection. A sequence-to-sequence method that uses the object information and motion information of the traffic scenes extracted by a state-of-the-art object detector and from optical flow, respectively, is proposed for automatic interaction detection. The proposed method generates a probability of interaction at each short interval (< 0.1 s) that represents the changing of interaction along a sequence. We obtain a baseline model that differentiates no interaction from interaction on the basis of the location and road user type from the detected object information. Compared with the baseline model, the empirical results of the proposed method demonstrate very accurate predictions for vehicle turning sequences with varying length.

DOI： 10.1109/IV47402.2020.9304554

Scopus

その他リンク： https://dblp.uni-trier.de/db/conf/ivs/ivs2020.html#ChengLSAMH20

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：Proceedings - 2019 International Conference on Computer Vision Workshop, ICCVW 2019  

Drivers obtain information on surrounding environment using their eyesights. Experienced eye-gaze behavior is needed when driving at places where multiple risks exist to prepare for and avoid them. In this work, we analyze the change in eye-gaze behavior in such situations while a driver gains experience on the operation of a robotic wheelchair. Accurate distance information in the traffic environment is important to analyze the eye-gaze behavior. However, almost all previous works analyze eye-gaze behavior in a 2D environment, so they could not obtain accurate distance information. For this reason, we analyze eye-gaze behavior in 3D space. Concretely, we developed a novel eye-gaze behavior analysis platform based on a robotic wheelchair and estimated the driver's attention in 3D space. We try to analyze the eye-gaze behavior considering a useful field-of-view in 3D space based on the distance information instead of only the fixation point to investigate the objects that a driver implicitly pays attention to and from where s/he focuses on them. Results show that novice drivers pay attention to a single risk at a time. In contrast, they pay more attention to multiple risks simultaneously as they gain experience. Additionally, we discuss what features are effective to model the eye-gaze behavior based on the results.

DOI： 10.1109/ICCVW.2019.00545

Web of Science

Scopus

その他リンク： https://dblp.uni-trier.de/db/conf/iccvw/iccvw2019.html#MaekawaAHMDKIM19

記述言語：英語   掲載種別：研究論文（学術雑誌）  

DOI： 10.1109/LRA.2019.2929999

Web of Science

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：2019 IEEE Intelligent Transportation Systems Conference, ITSC 2019  

In this study, we attempt to establish the numerical safety criteria for negotiating blind corners in personal mobility vehicles (PMVs). Safety should be the most important consideration in designing autonomous PMVs. However, determining the suitable trade-off between safety and speed is a weighty concern because speed is significantly compromised when performing overly safe navigation. We analyze the driving behavior of a robotic PMV operated by a human driver. The robotic PMV can measure the driver's gaze, and allows us to recognize both the pose of the PMV and the driver's visual attention on a 3D map. As a result, the occluded areas for the driver can be estimated. Then, potential colliding hazard obstacles (PCHOs) are simulated based on the occlusion. PCHOs refer to occluded obstacles that the driver encounters suddenly with which he cannot avoid collision. The participants of our experiments were one skillful and three non-skilled ones. Experimental results demonstrate that similar PCHOs are observed even when the driving styles of the participants are different. Additionally, the existence of a boundary that distinguishes expected and unexpected obstacles is indicated by investigating the parameters of the PCHOs. Finally, we conclude that the boundary could be utilized as a numerical criterion for ensuring safety while negotiating blind corners.

DOI： 10.1109/ITSC.2019.8917163

Web of Science

Scopus

その他リンク： https://dblp.uni-trier.de/db/conf/itsc/itsc2019.html#AkaiHMM19

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：IEEE Intelligent Vehicles Symposium, Proceedings  

This paper presents a comparison of driving behavior modeling methods based on hidden Markov models (HMMs) with driver's eye-gaze measurement and ego-vehicle localization. Original HMMs are sometimes insufficient to model real-world scenarios. To overcome these limitations, extended HMMs have been proposed, e.g., autoregressive input-output HMMs (AIOHMMs). This paper first details AIOHMMs and presents ways to use them for driving behavior modeling. We compare the performance for behavior modeling and maneuver discrimination for six types of HMMs. The driving data for this work was gathered in our university campus with a car-like vehicle. Experimental results suggest that the hidden states can properly represent the average of the driving actions when the driving behaviors are accurately modeled by the HMMs. It is also suggested that surrounding and past information can be used to flexibly model the relationship between driving actions and related information.

DOI： 10.1109/IVS.2019.8814287

Web of Science

Scopus

その他リンク： https://dblp.uni-trier.de/db/conf/ivs/ivs2019.html#AkaiHMALM19

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：Proceedings - 2018 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2018  

In this paper we present a method to learn how to drive in different types of blind intersections using expert driving data. We cluster different intersections based on the velocity of how drivers approach them, and train a linear SVM classifier for each class of intersection. Through clustering we found that there were three different classes of intersections in typical residential areas in Japan. We used inverse reinforcement learning (IRL) to build a driving model for each type of intersection. The models were trained from 308 trajectories traversed by 5 different drivers. The models and policies were implemented and evaluated in a ROS simulator where the agent is provided a global path, and upon it reaching an intersection, it selects the appropriate trained policy. By doing this, the simulated autonomous vehicle can perform proactive safe driving behaviors when approaching blind intersections.

DOI： 10.1109/SMC.2018.00064

Web of Science

Scopus

その他リンク： https://dblp.uni-trier.de/db/conf/smc/smc2018.html#SamaMATT18

Web of Science

担当区分：筆頭著者,　責任著者  

Web of Science

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：IEEE International Conference on Intelligent Robots and Systems  

Localization robustness against environment dynamics is significant for robots to achieve autonomous navigation in unmodified environments. A basic method of improving the robustness of a robot is considering the sensor observations obtained from mapped obstacles and using them for localizing the robot's pose. This study proposes an observation model that considers the class of sensor observations, where 'class' categorizes the sensor observations as those obtained from mapped and unmapped obstacles. In the proposed approach, the robot's pose and the class are estimated simultaneously. As a result, the robot's pose can be localized using the sensor observations obtained only from mapped obstacles. First, we evaluated the performance of the proposed approach using simulations. Further, we tested the proposed approach in a real-world mobile robot navigation competition, called 'Tsukuba Challenge,' held in Japan. The robustness and effectiveness of the proposed approach against environment dynamics were verified from the experimental results.

DOI： 10.1109/IROS.2018.8594146

Web of Science

Scopus

その他リンク： https://dblp.uni-trier.de/db/conf/iros/iros2018.html#AkaiMM18

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：IEEE International Conference on Intelligent Robots and Systems  

In this paper we present a data driven approach for safe and smooth autonomous navigation of a personal mobility vehicle (PMV) when facing moving obstacles such as people and bicycles in public pedestrian paths. In a period of three months, data from five different persons driving the robotic PMV in an outdoor environment while facing pedestrians were collected. 2465 clean tracks around the vehicle together with PMVs trajectories were collected. We performed an analysis of the parameters involved for human-driven smooth navigation. Relevant parameters regarding PMV-Human interaction included distance to moving objects, passing side and velocities. Moreover, data suggests the existence of a social navigational distance for the PWv. For autonomous navigation we implemented a Frenet planner to achieve safe and smooth navigation for the passenger and pedestrians around. Experimental results in real pedestrian paths show that the PMV is capable of smoothly following its path while facing pedestrians and bicycles.

DOI： 10.1109/IROS.2018.8593902

Web of Science

Scopus

その他リンク： https://dblp.uni-trier.de/db/conf/iros/iros2018.html#MoralesAM18

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC  

In this paper, a slope-robust cascaded ground segmentation in 3D point cloud for autonomous vehicles is presented. In many challenging terrains encountered by autonomous vehicles where the ground does not have a simple planar shape such as sloped roads, many existing ground segmentation algorithms fail. The proposed algorithm aims to correctly segment ground points in scans where these challenging terrains are present. The proposed method consists of two main steps. First, filtering the majority of non-ground points using the geometry of the sensor and the distance between consecutive rings in the scan. In the second step, multi-region RANSAC plane fitting is used to separate remaining non-ground points from ground points in the scan. The 3D data was taken and partially labeled for quantitative evaluation. The experimental results were outstanding as the proposed algorithm could segment the ground correctly in various challenging terrains. The proposed algorithm could correctly segment ground points in the scan even in sloped terrains and achieved higher accuracy than other algorithms used in the evaluation.

DOI： 10.1109/ITSC.2018.8569534

Web of Science

Scopus

その他リンク： https://dblp.uni-trier.de/db/conf/itsc/itsc2018.html#NarksriTNMAK18

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：IEEE  

© 2018 IEEE. This paper presents an approach for predictive driving when facing blind intersections based on expert data. Expert drivers anticipate and avoid potential dangerous situations. In most cases these complex behaviors cannot be reproduced by state of the art planning approaches. We present an analysis of expert drivers while passing through blind intersections, we extract useful driving features to model the intersection and propose a cost function based on those features. We use inverse reinforcement learning to extract a feature-based cost function and learn its parameters from driver data. Finally, feature weights are computed based on collected expert driving data (using 211 trajectories). Evaluation was performed in terms of trajectory and speed using modified Hausdorff distance. Experimental results show that the planner is capable of computing trajectories comparable to those ones of the expert drivers when facing blind intersections.

DOI： 10.1109/ITSC.2018.8569931

Web of Science

Scopus

その他リンク： https://dblp.uni-trier.de/db/conf/itsc/itsc2018.html#SaikiAYM18

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC  

To robustly localize the pose of an ego vehicle within a dynamic environment, it is important to model the sensor measurements precisely, including changes in the environment. This study describes the observation models developed for localization performed in highly dynamic environments, and presents the results of comparing these models. In this study, four observation models, including our previously proposed model, were compared by conducting a simulation. The models had different ways of coping with changes in the environment, and produced different results. Moreover, the comparison results revealed that each model had its own advantages and disadvantages. Finally, we demonstrated that our previously proposed model can achieve satisfactory performance in terms of computation complexity and estimation accuracy.

DOI： 10.1109/ITSC.2018.8569967

Web of Science

Scopus

その他リンク： https://dblp.uni-trier.de/db/conf/itsc/itsc2018.html#AkaiMHM18

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC  

In this paper we present a work on encoding, clustering and modeling expert driver behaviors to be reproduced by an autonomous driving car agent. We collected speed, brake, steering wheel and acceleration data from an expert driving in typical Japanese suburban areas. We grouped together consecutive data in a sliding window as the input to a fully connected deep autoencoder for dimension reduction. We then clustered the encoded driving data into 9 different behaviors. For each behavior class, we modeled the speed using a fit of same clustered data and tested the models in a ROS car simulator. Results show that the models created from the clusters could represent different driving behaviors on various roads. Experimental simulations show that the proposed approach can reproduce speed behavior comparable to that of the expert drivers even in new environments.

DOI： 10.1109/ITSC.2018.8569245

Web of Science

Scopus

その他リンク： https://dblp.uni-trier.de/db/conf/itsc/itsc2018.html#SamaMALTT18

記述言語：英語   掲載種別：研究論文（学術雑誌）   出版者・発行元：Advanced Robotics  

In this study, we propose a novel localization approach that simultaneously estimates the reliability of estimation results. In the approach, a convolutional neural network (CNN) is used to make decision whether the localization process has failed or not. We train the CNN using a dataset that includes successful localization results and faults. However, the decision will contain some noise and many misdetection results may occur when the decision made by the CNN is used directly to detect faults. Therefore, we estimate both a robot's pose and reliability of the localization results based on the decision. To simultaneously estimate the robot's pose and reliability, we propose a new graphical model and implement a Rao–Blackwellized particle filter based on the model. We evaluated the proposed approach based on simulations and actual environments, which showed that the reliability estimated by the proposed approach can be used as an exact criterion for detecting localization faults. In addition, we show that the proposed approach can be applied in actual environments even when a dataset created from a simulation is used to train the CNN.

DOI： 10.1080/01691864.2018.1509726

Web of Science

Scopus

その他リンク： https://dblp.uni-trier.de/db/journals/ar/ar32.html#AkaiSM18

Web of Science

Web of Science

Web of Science

記述言語：英語   掲載種別：研究論文（学術雑誌）   出版者・発行元：富士技術出版株式会社  

Autonomous mobile robot navigation in real unmodified outdoor areas frequented by people on their business, children playing, fast running bicycles, and even robots, remains a difficult challenge. For eleven years, the Tsukuba Challenge Real World Robot Challenge (RWRC) has brought together robots, researchers, companies, government, and ordinary citizens, under the same outdoor space to push forward the limits of autonomous mobile robots. For the Tsukuba Challenge 2017 participation, our team proposed to study the problem of sensors-to-actuators navigation (also called End-to-End), this is, having the robot to navigate towards the destination on a complex path, not only moving straight but also turning at intersections. End-to-End (E2E) navigation was implemented using a convolutional neural network (CNN): the robot learns how to go straight, turn left, and turn right, using camera images and trajectory data. E2E network training and evaluation was performed at Nagoya University, on similar outdoor conditions to that of Tsukuba Challenge 2017 (TC2017). Even thought E2E was trained on a different environment and conditions, the robot successfully followed the designated trajectory in the TC2017 course. Learning how to follow the road no matter the environment is of the key attributes of E2E based navigation. Our E2E does not perform obstacle avoidance and can be affected by illumination and seasonal changes. Therefore, to improve safety and add fault tolerance measures, we developed an E2E navigation approach with model-based system as backup. The model-based system is based on our open source autonomous vehicle software adapted to use on a mobile robot. In this work we describe our approach, implementation, experiences and main contributions.

DOI： 10.20965/jrm.2018.p0563

Web of Science

Scopus

CiNii Research

記述言語：英語   掲載種別：研究論文（学術雑誌）   出版者・発行元：富士技術出版株式会社  

Navigation in social environments, in the absence of traffic rules, is the difficult task at the core of the annual Tsukuba Challenge. In this context, a better understanding of the soft rules that influence social dynamics is key to improve robot navigation. Prior research attempts to model social behavior through microscopic interactions, but the resulting emergent behavior depends heavily on the initial conditions, in particular the macroscopic setting. As such, data-driven studies of pedestrian behavior in a fixed environment may provide key insight into this macroscopic aspect, but appropriate data is scarcely available. To support this stream of research, we release an open-source dataset of dynamic object trajectories localized in a map of 2017 Tsukuba Challenge environment. A data collection platform equipped with lidar, camera, IMU, and odometry repeatedly navigated the challenge’s course, recording observations of passersby. Using a background map, we localized ourselves in the environment, removed the static background from the point cloud data, clustered the remaining points into dynamic objects and tracked their movements over time. In this work, we present the Tsukuba Challenge Dynamic Object Tracks dataset, which features nearly 10,000 trajectories of pedestrians, cyclists, and other dynamic agents, in particular autonomous robots. We provide a 3D map of the environment used as global frame for all trajectories. For each trajectory, we provide at regular time intervals an estimated position, velocity, heading, and rotational velocity, as well as bounding boxes for the objects and segmented lidar point clouds. As additional contribution, we provide a discussion which focuses on some discernible macroscopic patterns in the data.

DOI： 10.20965/jrm.2018.p0598

Web of Science

Scopus

CiNii Research

記述言語：英語   掲載種別：研究論文（学術雑誌）   出版者・発行元：富士技術出版株式会社  

This paper presents a teaching-playback navigation method that does not require a consistent map built using simultaneous localization and mapping (SLAM). Many open source projects related to autonomous navigation including SLAM have been made available recently; however, autonomous mobile robot navigation in large-scale environments is still difficult because it is difficult to build a consistent map. The navigation method presented in this paper uses several partial maps to represent an environment map. In other words, the complex mapping process is not necessary to begin autonomous navigation. In addition, the trajectory that the robot travels in the mapping phase can be directly used as a target path. As a result, teaching-playback autonomous navigation can be achieved without any off-line processes. We tested the navigation method using log data taken in the environment of the Tsukuba Challenge and the testing results show its performance. We provide source code for the navigation method, which includes modules required for autonomous navigation (https://github. com/NaokiAkai/AutoNavi).

DOI： 10.20965/jrm.2018.p0591

Web of Science

Scopus

CiNii Research

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：2018 3rd International Conference on Control and Robotics Engineering, ICCRE 2018  

In order for autonomous vehicles to learn how to naturally navigate through an intersection, we present a method of learning from expert drivers using inverse reinforcement learning. We cluster different intersections according to how experts drive through them and train a model based on each class of intersection. With these models to choose from, as the agent encounters various situations, it can retrieve the corresponding model and execute the most fit policy. The models were trained from 308 trajectories recorded from 5 different drivers at 3 intersections. These clusters were then used to classify a further 5 more intersections. The approach is evaluated in a simulator where we provide a global path to be followed by the vehicle where at each intersection it drives according to the trained policies.

DOI： 10.1109/ICCRE.2018.8376469

Web of Science

Scopus

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：IEEE Conference on Intelligent Transportation Systems, Proceedings, ITSC  

In this study, we developed an autonomous driving system for mountainous public roads. Three-dimensional normal distribution transform (NDT) scan matching is employed for localization and a model predictive controller is utilized for vehicle motion control. In order to increase the robustness of the localization method, the estimated poses are computed by an extended Kalman filter using dead reckoning and NDT information. The uncertainty of the pose estimated by NDT is determined by using the Hessian matrix computed in the optimization process for scan matching. We conducted experiments in a public road environment over 20 times and all of the tests were successful. The experimental results confirmed that the autonomous driving system can operate reliably in mountainous public roads. In addition, the evaluation results obtained for the localization method showed that accurate and robust localization can be achieved in mountainous rural environments.

DOI： 10.1109/ITSC.2017.8317797

Web of Science

Scopus

Web of Science

Web of Science

Web of Science

Web of Science

Web of Science

Web of Science

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）  

DOI： 10.1109/IVS.2018.8500625

Web of Science

その他リンク： https://dblp.uni-trier.de/db/conf/ivs/ivs2018.html#AkaiMM18

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：IEEE International Conference on Intelligent Robots and Systems  

This paper presents a model for safe driving at blind intersections and its integration to a local planner based on a Frenet frame. The model predicts potential moving obstacles from blind intersections to proactively slow down to avoid potential collisions. The derivation of the model is described and its parameters are detailed. The local planner computes smooth trajectories with smooth velocity profiles so that the vehicle can follow the paths without jerk and sudden accelerations resulting in safe and comfortable navigation. Experimental results in simulation and in the real field with an autonomous car, show that the proposed predictive driving framework can reproduce human expert driver's trajectories and velocities when facing blind intersections.

DOI： 10.1109/IROS.2017.8206185

Web of Science

Scopus

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems  

This paper presents a fusion of monocular camera-based metric localization, IMU and odometry in dynamic environments of public roads. We build multiple vision-based maps and use them at the same time in localization phase. For the mapping phase, visual maps are built by employing ORB-SLAM and accurate metric positioning from LiDAR-based NDT scan matching. This external positioning is utilized to correct for scale drift inherent in all vision-based SLAM methods. Next in the localization phase, these embedded positions are used to estimate the vehicle pose in metric global coordinates using solely monocular camera. Furthermore, to increase system robustness we also proposed utilization of multiple maps and sensor fusion with odometry and IMU using particle filter method. Experimental testing were performed through public road environment as far as 170 km at different times of day to evaluate and compare localization results of vision-only, GNSS and sensor fusion methods. The results show that sensor fusion method offers lower average errors than GNSS and better coverage than vision-only one.

DOI： 10.1109/MFI.2017.8170431

Web of Science

Scopus

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：2017 International Conference on Indoor Positioning and Indoor Navigation, IPIN 2017  

Magnetic fields are used for localization and navigation in the field of robotics. In recent years, because of the spread of mobile devices equipped with magnetic sensors (e.g., smart phones), the use of magnetic fields has been extensive, especially for position tracking of mobile devices. One example application of such tracking is in identifying the position of a person with a mobile device. Development of this application requires a three-dimensional (3D) magnetic map that represents the magnetic distribution of a 3D environment since the device moves around in 3D space. It is, however, difficult to construct a 3D magnetic map of a large-scale environment because measuring the magnetic field is time consuming and expensive. In this paper we propose an efficient method for mapping the 3D magnetic field of a large-scale environment. The method uses a mobile manipulator to measure the 3D magnetic field, enabling 3D magnetic data to be automatically collected. Moreover, the method uses Gaussian processes (GPS) for regression of the magnetic field. In this study, we first evaluate the performance of the GPS and then describe the measurement robot. In an experiment, a 3D magnetic field of an indoor environment is visualized by using this method and the performance of the presented method is demonstrated.

DOI： 10.1109/IPIN.2017.8115960

Web of Science

Scopus

Web of Science

Web of Science

記述言語：英語   掲載種別：研究論文（学術雑誌）   出版者・発行元：富士技術出版株式会社  

Planning is one of the cornerstones of autonomous robot navigation. In this paper we introduce an open source planner called “OpenPlanner” for mobile robot navigation, composed of a global path planner, a behavior state generator and a local planner. Open-Planner requires a map and a goal position to compute a global path and execute it while avoiding obstacles. It can also trigger behaviors, such as stopping at traffic lights. The global planner generates smooth, global paths to be used as a reference, after considering traffic costs annotated in the map. The local planner generates smooth, obstacle-free local trajectories which are used by a trajectory tracker to achieve low level control. The behavior state generator handles situations such as path tracking, object following, obstacle avoidance, emergency stopping, stopping at stop signs and traffic light negotiation. OpenPlanner is evaluated in simulation and field experimentation using a non-holonomic Ackerman steering-based mobile robot. Results from simulation and field experimentation indicate that OpenPlanner can generate global and local paths dynamically, navigate smoothly through a highly dynamic environments and operate reliably in real time. OpenPlanner has been implemented in the Autoware open source autonomous driving framework’s Robot Operating System (ROS).

DOI： 10.20965/jrm.2017.p0668

Web of Science

Scopus

CiNii Research

記述言語：英語   掲載種別：研究論文（学術雑誌）   出版者・発行元：富士技術出版株式会社  

This paper describes our approach to perform robust monocular camera metric localization in the dynamic environments of Tsukuba Challenge 2016. We address two issues related to vision-based navigation. First, we improved the coverage by building a custom vocabulary out of the scene and improving upon place recognition routine which is key for global localization. Second, we established possibility of lifelong localization by using previous year’s map. Experimental results show that localization coverage was higher than 90% for six different data sets taken in different years, while localization average errors were under 0.2 m. Finally, the average of coverage for data sets tested with maps taken in different years was of 75%.

DOI： 10.20965/jrm.2017.p0685

Web of Science

Scopus

CiNii Research

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：IEEE Intelligent Vehicles Symposium, Proceedings  

This paper presents a model for velocity control in blind corners and intersections based on expert driver data. Accurate expert driver data was collected with a car equipped with a 3D LiDAR and high definition maps. A model based on human expert driver data is used to control the velocity of the ego-vehicle when facing blind intersections. The model regulates ego-vehicle velocity based on the visibility of the road at the blind intersection. As the vehicle approximates the intersection and crossing roads are not visible, the vehicle slows down, then as the roads become visible the vehicle accelerates. Experimental results show the performance of the velocity model compared towards 270 trajectories taken from 7 expert drivers towards 6 different intersections without mandatory stops.

DOI： 10.1109/IVS.2017.7995830

Web of Science

Scopus

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：IEEE Intelligent Vehicles Symposium, Proceedings  

In this paper, we present a localization approach that is based on a point-cloud matching method (normal distribution transform 'NDT') and road-marker matching based on the light detection and ranging intensity. Point-cloud map-based localization methods enable autonomous vehicles to accurately estimate their own positions. However, accurate localization and 'matching error' estimations cannot be performed when the appearance of the environment changes, and this is common in rural environments. To cope with these inaccuracies, in this work, we propose to estimate the error of NDT scan matching beforehand (off-line). Then, as the vehicle navigates in the environment, the appropriate uncertainty is assigned to the scan matching. 3D NDT scan matching utilizes the uncertainty information that is estimated off-line, and is combined with a road-marker matching approach using a particle-filtering algorithm. As a result, accurate localization can be performed in areas in which 3D NDT failed. In addition, the uncertainty of the localization is reduced. Experimental results show the performance of the proposed method.

DOI： 10.1109/IVS.2017.7995900

Web of Science

Scopus

Web of Science

Web of Science

Web of Science

Web of Science

Web of Science

Web of Science

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：Proceedings - 4th IEEE International Conference on Cyber-Physical Systems, Networks, and Applications, CPSNA 2016  

In this paper, we aim to explore path following. We implement a path following component by referring to the existing Pure Pursuit algorithm. Using the simulation and field operational test, we identified the problem in the path following component. The main problems identified were with respect to vehicles meandering off the path, turning a corner, and the instability of steering control. Therefore, we apply some modifications to the Pure Pursuit[1] algorithm. We have also conducted the simulation and field operational tests again to evaluate these modifications.

DOI： 10.1109/CPSNA.2016.10

Web of Science

Scopus

その他リンク： https://dblp.uni-trier.de/db/conf/cpsna/cpsna2016.html#OhtaATKE16

Web of Science

記述言語：英語   掲載種別：研究論文（学術雑誌）   出版者・発行元：富士技術出版株式会社  

The Real World Robot Challenge (RWRC), a technical challenge for mobile outdoor robots, has robots automatically navigate a predetermined path over 1 km with the objective of detecting specific persons. RWRC 2015 was conducted in the rain and every robot could not complete the mission. This was because sensors on the robots detected raindrops and the robots then generated unexpected behavior, indicating the need to study the influence of rain on mobile navigation systems – a study clearly not yet sufficient. We begin by describing our robot’s waterproofing function, followed by investigating the influence of rain on the external sensors commonly used in mobile robot navigation and discuss how the robot navigates autonomous in the rain. We conducted navigation experiments in artificial and actual rainy environments and those results showed that the robot navigates stably in the rain.

DOI： 10.20965/jrm.2016.p0441

Web of Science

Scopus

CiNii Research

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：IEEE  

© 2015 IEEE. This paper proposes a novel navigation method based on topological magnetic and geometric maps for outdoor mobile robots. In this method, a state of a robot is represented by a travel distance and a lateral error, which is a distance from the travel path to the robot. In order to estimate the travel distance, a magnetic map which represents a magnetic field of the travel path is used. Since the magnetic field does not depend on moving objects, the travel distance can be robustly estimated against changes in geometric situations. However, deviating from the travel path is a fatal problem since the magnetic map does not record other magnetic fields of the travel path. To compensate this deviation, the lateral error is estimated by using geometric landmarks. Since this estimation is performed after the travel distance estimate, the lateral error can be stably estimated even if many moving objects surround the robot. As a result, the robot exactly navigates the travel path. Simulation and actual experiments are conducted to show the effectiveness and performance of the proposed method.

DOI： 10.1109/SII.2015.7404945

Web of Science

Scopus

その他リンク： https://dblp.uni-trier.de/db/conf/sii/sii2015.html#AkaiO15

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：IEEE  

© 2015 IEEE. The magnetic field that exists in an indoor environment includes rich magnetic fluctuations because buildings contain many magnetized materials (e.g., steel frames). These fluctuations can be used as landmarks, the use of which requires the creation of a magnetic map representing the distribution of the magnetic field. It is, however, difficult to build a large-scale magnetic map because of the narrow measurement range of a magnetic sensor. This paper proposes an efficient method for collecting magnetic data using a mobile robot and a method for building a magnetic map using Gaussian processes. The use of these methods make it possible to build a large-scale magnetic map efficiently. Moreover, this paper presents a particle filter-based localization method based on the magnetic map. The presented system enables a robot to identify its own position in large-scale buildings. Experiments are used to demonstrate the performance and usefulness of the presented system.

DOI： 10.1109/IROS.2015.7354010

Web of Science

Scopus

その他リンク： https://dblp.uni-trier.de/db/conf/iros/iros2015.html#AkaiO15

記述言語：英語   掲載種別：研究論文（学術雑誌）   出版者・発行元：FUJI TECHNOLOGY PRESS LTD  

Copyright 2015, Fuji Technology Press , All Rights Reserved. Extracting the color of a target object from images in environments with different illumination conditions, such as outdoors, is difficult because color performance changes easily. The novel color extraction we propose enables the exact color of a target object to be extracted using multiple photographs taken with different exposure times. The object’s color performance transits due to changes in exposure time. This transition is the same as when environmental light sources do not change significantly. In outdoor environment, most situations are regarded as that situation. We first indicate this in an experimental analysis, then detail our proposal. Our method evaluates transition and realizes precise color extraction of target objects in outdoors. We apply this method to an orange cap in the Tsukuba Real-World Robot Challenge. Through experiments, we show that the cap is detected accurately in different environments and discuss the method’s effectiveness and usefulness in the real world.

DOI： 10.20965/jrm.2015.p0365

Web of Science

Scopus

記述言語：英語   掲載種別：研究論文（学術雑誌）   出版者・発行元：FUJI TECHNOLOGY PRESS LTD  

Copyright 2015, Fuji Technology Press , All Rights Reserved. Held in Japan every year since 2007, the Real World Robot Challenge (RWRC) is a technical challenge for mobile robots. Every robot is given the missions of traveling a long distance and finding specific persons autonomously. The robots must also have an affinity for people and be remotely monitored. In order to complete the missions, we developed a new mobile robot, SARA, which we entered in RWRC 2014. The robot successfully completed all of the missions of the challenge. In this paper, the systems we implemented are detailed. Moreover, results of experiments and of the challenge are presented, and knowledges we gained through the experience are discussed.

DOI： 10.20965/jrm.2015.p0327

Web of Science

Scopus

掲載種別：研究論文（学術雑誌）  

© 2014, Akai et al.; licensee Springer. Background: In order for a robot to autonomously run in outdoor environments, a robust and stable navigation method is necessary. Especially, to run in real-world environments, robustness against moving objects is important since many pedestrians and bicycles come and go. Magnetic field, which is not influenced by the moving objects, is considered to be an effective information for autonomous navigation.Methods: Localization technique using a magnetic map, which records ambient magnetic field, has been proposed. The magnetic map is expressed as a linear map. When using this linear magnetic map, swerving from the desired path is a fatal problem. It is because that the magnetic map contains only magnetic data on a desired path. In the paper, we propose a novel navigation method which allows a robot to precisely navigate on a desired path even if localization is performed on the basis of the linear magnetic map. The navigation is performed by using a control method based on a DCS (Distributed Control System). In the system, several navigation modules are executed in parallel, and they independently control the robot by using magnetic and geometric landmarks.Results and discussion: We conducted three navigation experiments. Our robot could perfectly accomplish all navigation even if it was disturbed by many moving objects during the navigation.Conclusions: The control method based on the DCS could switch the navigation module for controlling the robot to cope against the change of its surroundings. The precise and robust navigation was achieved with the proposed method.

DOI： 10.1186/s40648-014-0021-8

Scopus

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：IEEE  

© 2014 IEEE. Realizing robots' controlling in controlling way of saving dof has a broad prospect and applied space using control technology. The paper discussed controlling horses using reins as inspiration, realizing the operation of mobile equipment of reins' control. The experiment confirmed the feasibility of operation by the first stage; Comparing the operating system of reins with the operating system of games' handle that people are very familiar by the experimental research of the second stage, getting the conclusion that the operating of reins is equivalent to handles' operation, and the evaluations of the implementation is better than the handles'. The test results show that the control system is very accordant for intuitive feelings of the user of mobile devices' control demand, and can skillfully master the main point of the operation in a very short time. The results of studying provide a useful way of thinking for the development and evaluation of the personal mobile way.

DOI： 10.1109/ICIEA.2014.6931238

Web of Science

Scopus

記述言語：英語   掲載種別：研究論文（学術雑誌）   出版者・発行元：FUJI TECHNOLOGY PRESS LTD  

© 2014, Fuji Technology Press. All rights reserved. We developed MAUV, an autonomous mobile robot that has navigation using two types of landmarks; ambient magnetic and geometric. This enables the robot to localize robustly in actual outdoor environments. The robot achieved missions in Tsukuba Challenge 2011, 12, and 13.

DOI： 10.20965/jrm.2014.p0657

Web of Science

Scopus

記述言語：英語   掲載種別：研究論文（学術雑誌）   出版者・発行元：FUJI TECHNOLOGY PRESS LTD  

© 2014, Fuji Technology Press. All rights reserved. A mobility robot “NENA” which can carry one person was developed by Utsunomiya University. The robot was developed based on the concept called “Design Framework” and it allowed the robot to equip with functions needed for manual driving and autonomous running and acceptable design for people. The robot fulfilled safety required for mobility robots used in the Tsukuba Mobility Robot Experimental Zone.

DOI： 10.20965/jrm.2014.p0659

Web of Science

Scopus

記述言語：英語   掲載種別：研究論文（学術雑誌）   出版者・発行元：FUJI TECHNOLOGY PRESS LTD  

For the Real World Robot Challenge (RWRC) 2013, a new task was established: every robot was required to search for designated persons. In this paper, therefore, we consider the difficulty of the task and construct a navigation strategy to achieve the task. To navigate a robot on the basis of the strategy, long distance navigation is necessary. We have developed a unique navigation method based on magnetic and geometric landmarks on environmental structures in various locations. This method allows a robot to robustly localize by evaluating the reliability of magnetic and geometric landmarks. By using this method, a robot can navigate stably, even if there are no existing landmarks to serve as objects. We achieved autonomous navigation over long distances and successfully searched out designated persons as the challenge of the RWRC2013. This paper presents our navigation method and discusses long distance navigation using the method.

DOI： 10.20965/jrm.2014.p0158

Web of Science

Scopus

記述言語：英語   掲載種別：研究論文（学術雑誌）   出版者・発行元：FUJI TECHNOLOGY PRESS LTD  

In Real World Robot Challenge 2013, a mission was added that had robots search for a person wearing clothes featuring unique colors. We focus on the layout of such clothes with the aim of detecting persons wearing them by applying color extraction. Color extraction is improved by preprocessing of a clipping image from the robot's vision and possibly extracting colors worn by target persons stably in natural light. Persons are detected by simply evaluating the layout of target colors. Our robots were equipped with person detection for this challenge and have detected all targeted persons. This paper describes considerations about person detection performance based on pre- and postchallenge results.

DOI： 10.20965/jrm.2014.p0151

Web of Science

Scopus

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：IEEE  

© 2014 IEEE. This paper proposes a novel color extraction method using multiple images taken with different exposure time. Although using the multiple images is a famous technique to recover a high dynamic range radiance map, we do not use it. Alternatively, we focus on that any color performance is uniformly transited by changing exposure time even if under various illumination conditions. In this paper, we indicate it experimentally and develop a color extraction method with this characteristic. In the experiment, we set orange color as desired color and conducted color extraction to orange, red, and yellow colors in outdoor environments. Our proposed method exactly extracted only orange color from images under extreme exposure conditions.

DOI： 10.1109/SII.2014.7028050

Web of Science

Scopus

記述言語：英語   掲載種別：研究論文（国際会議プロシーディングス）   出版者・発行元：IEEE  

For realizing more stable outdoor navigation for mobile robots, this paper proposes a localization method using a magnetic sensor and a Light Detection and Ranging (LIDAR). In the proposed method, Monte Carlo Localization (MCL) using the LIDAR and a determination method of a heading direction using the ambient magnetic field are combined. In other words, the proposal distribution becomes dense at the true state of the robot by using the ambient magnetic field. The determination method is based on the advantage of the magnetic navigation proposed by us. By the proposed method, the robot enabled to navigate with accuracy in the outdoor environment, since the robust localization is realized. The effectiveness of the proposed method is shown through experiments. Moreover, two robots implemented the proposed method achieved the task of Real World Robot Challenge 2012. This means that the proposed method is effective for real world navigation. © 2013 IEEE.

DOI： 10.1109/sii.2013.6776657

Web of Science

Scopus

その他リンク： https://dblp.uni-trier.de/db/conf/sii/sii2013.html#AkaiHIO13

記述言語：日本語   出版者・発行元：一般社団法人 日本機械学会  

<p>This paper presents a misalignment recognition method using a Markov random field with fully connected latent variables for LiDAR-based localization. The major difficulty for the misalignment recognition is that considering entire relation of sensor measurement in localization is impossible because it must be assumed that the sensor measurement is independent to one another. The presented method enables to consider the entire relation via the fully connected latent variables. This paper also presents a calculation method of localization failure probability based on the misalignment recognition. Experiments show that the presented method can exactly detect misalignment even though partial sensor measurement overlaps with a map and can exactly recognize success and failure localization results.</p>

DOI： 10.1299/jsmermd.2020.2P1-K14

CiNii Research

J-GLOBAL

記述言語：日本語  

J-GLOBAL

J-GLOBAL

J-GLOBAL

J-GLOBAL

記述言語：日本語   出版者・発行元：一般社団法人 日本機械学会  

<p>This paper presents a driving behavior modeling method using autoregressive input-output hidden Markov models (AIOHMMs). First, model parameter learning and discrimination ways using the AIOHMMs are detailed. In experiments, we model four driving maneuvers with driver's eye-gaze and ego-vehicle localization information and compare maneuver discrimination performances by four types of HMMs. Additionally, we discuss modeling performance by the AIOHMMs through the experiments.</p>

DOI： 10.1299/jsmermd.2019.2A1-E05

CiNii Research

J-GLOBAL

J-GLOBAL

記述言語：日本語   出版者・発行元：公益社団法人 自動車技術会  

自車両位置認識は自動運転における基幹技術であり，位置認識の失敗は自動運転自体の失敗へ直結する危険がある．しかし，その認識結果の正誤を保証する術はない．本稿では，位置認識の正誤を学習した学習機の出力を新たな観測変数として利用し，ロバストに位置認識結果の正誤（信頼度）を推定するモデルを提案・検証する．

DOI： 10.11351/jsaeronbun.50.609

CiNii Books

CiNii Research

記述言語：日本語   出版者・発行元：公益社団法人 計測自動制御学会  

<p>This paper presents a localization approach that simultaneously estimates a robot's pose and class of sensor observations, where "class" categorizes the sensor observations as those obtained from known and unknown objects on a given geometric map. The proposed approach is implemented using Rao-Blackwellized particle filtering algorithm. The robot's pose can be robustly estimated utilizing sensor observations obtained from the only known objects by the simultaneous estimation. The proposed approach is efficient in terms of computational complexity because its complexity is same as that of the likelihood field model. Performance of the proposed approach was shown through experiments using a 2D LiDAR simulator.</p>

DOI： 10.9746/sicetr.55.745

CiNii Books

CiNii Research

J-GLOBAL

J-GLOBAL

記述言語：日本語   出版者・発行元：一般社団法人 人工知能学会  

DOI： 10.11517/jjsai.34.2_206

CiNii Books

CiNii Research

J-GLOBAL

その他リンク： http://id.nii.ac.jp/1004/00009675/

J-GLOBAL

J-GLOBAL

記述言語：日本語   出版者・発行元：一般社団法人 日本機械学会  

<p>This paper presents a novel localization approach that simultaneously estimates a robot's pose and reliability of its estimation. To estimate the reliability, a convolutional neural network (CNN) is used as a decision maker for distinguishing whether localization has failed. The CNN, however, sometimes makes wrong decisions. To reduce influence of the wrong decisions, Rao-Blackwellized particle filter (RBPF) is employed. The reliability can be robustly estimated using the RBPF and it exactly describes successful and failure localization results. Exact performance of the reliability is shown through the experiments.</p>

DOI： 10.1299/jsmermd.2018.1A1-J01

CiNii Research

J-GLOBAL

記述言語：日本語   出版者・発行元：公益社団法人 自動車技術会  

自動運転を行うためには，走行すべき経路との相対位置関係や，注視すべき物体の情報を得ることが有用であり，そのためにも，自己位置推定は重要な技術である．本稿では，デッドレコニングとマルチレイヤーLIDARによる位置推定結果を融合することで，一般道における高精度位置推定，および自動運転を達成したので報告する．

DOI： 10.11351/jsaeronbun.49.675

CiNii Books

CiNii Research

J-GLOBAL

記述言語：日本語   出版者・発行元：技術情報協会  

J-GLOBAL

記述言語：日本語   出版者・発行元：国際交通安全学会  

CiNii Books

J-GLOBAL

J-GLOBAL

記述言語：日本語   出版者・発行元：一般社団法人 日本機械学会  

<p>A LIDAR is commonly used for autonomous mobile navigation. It detects raindrops under rainy situations since its output laser beams collide the drops. This influences against performance of the navigation, for example obstacle avoidance. In this study, we first investigate influence of rain against the LIDAR and then propose a coping method, which contains two ways, for reducing the rain's influence. The first way is a hardware-based coping method that is to add additional waterproof parts. The second way is a software-based coping method that is to remove raindrops from the LIDAR readings like a filtering algorithm. By using these methods, number of raindrop detection is significantly reduced. As a result, autonomous navigation can be performed in rainy situations and its performance is verified in a man-made environment.</p>

DOI： 10.1299/jsmermd.2016.1A1-07b4

J-GLOBAL

記述言語：日本語   出版者・発行元：一般社団法人 日本機械学会  

<p>Extracting predetermined colors under various illumination conditions like outdoor is difficult. To overcome the problem, we focused on color transition which is obtained by changing camera's exposure and proposed a color extraction method using it. Although this method improves color extraction accuracy from simple color extraction methods which uses a color space such as xy chromaticity diagram or HSV color space, some problems still exist. The objective of this study is to extend this method and evaluate its performance. To extend this method, we propose a new color extraction method using two color transitions, hue and saturation transitions. This performance is evaluated by applying it to a task of the Tsukuba Challenge that is to a find person who wears specific color clothes.</p>

DOI： 10.1299/jsmermd.2016.2A1-19b2

J-GLOBAL

記述言語：日本語   出版者・発行元：一般社団法人 日本ロボット学会  

This paper proposes a novel loop-closure detection method based on localization using residual magnetism. Although the method uses only a magnetic sensor as external sensor, accurate loop-closure detection can be performed. This is because that precisely distinguishing of magnetic pattern is realized by using normalized cross-correlation. In addition, the method has usefulness that loop-closure detection is executed so fast. The effectiveness and usefulness of the method are shown through experiments.

DOI： 10.7210/jrsj.34.397

CiNii Books

CiNii Research

J-GLOBAL

J-GLOBAL

J-GLOBAL

J-GLOBAL

J-GLOBAL

J-GLOBAL

J-GLOBAL

J-GLOBAL

J-GLOBAL

記述言語：日本語   出版者・発行元：一般社団法人 日本機械学会  

A SLAM (Simultaneous Localization and Mapping) problem is major in mobile robotics field about past two decades. In order to solve the problem, a camera and a LIDAR (Light Detection and Ranging) are generally used. In contrast, this paper proposes a new solution for the problem using a magnetic sensor. Our method is simple since an observation model in RBPF (Rao-Blackwellized Particle Filter)-SLAM is replaced by that of a magnetic sensor. However, magnetic sensor-based SLAM has a problem that is so narrow measurement range of the sensor. To deal with the problem, we use a heuristic method to determine surround magnetic field. We conducted experiments in actual outdoor environments including loops and verified its accuracy by using a LIDAR. Through the experiments, it was shwon that our method can close loops and build consistent maps; magnetic and geometric.

DOI： 10.1299/jsmermd.2015._2A2-M05_1

J-GLOBAL

記述言語：日本語   出版者・発行元：公益社団法人 計測自動制御学会  

In Tsukuba Challenge 2013, every robot had to navigate on a given path and detect specific persons wearing showy color clothes. There are many ideal functions for achieving the mission. It is, however, difficult to implement all ideal functions since complex algorithms are required. This paper, therefore, considers simplified functions for achieving the mission even if complex algorithms are not implemented. Our robot can run long distance by using a unique localization method which uses both of magnetic and geometric landmarks. Moreover, it can detect the target based on a color extraction method. These abilities enable the robot to exactly work the simple functions. Through the experiments, it is shown that our robot can exactly achieve the given mission by using only the simplified functions.

DOI： 10.9746/sicetr.51.24

CiNii Books

J-GLOBAL

記述言語：日本語   出版者・発行元：一般社団法人 日本機械学会  

This report describes development of a mobile robot's armor which is enable to detect pushing or touching with any objects on its surface. In order to achieve the purpose, it is necessary to design suitable layout of strain gauges as haptic sensors on the armor when changing surface of the armor such as widely bends or distortion with pushing. The armor should be shapely, and it is to be desired that number of haptic sensors is reduced. Therefore, it is required to detect efficiently changing on the surface by haptic sensors in even small number. In this report, it is shown that the layout by 34 sets of strain gauges as haptic sensors is designed based on analysis of stress on surface of the armor.

DOI： 10.1299/jsmermd.2015._1P1-V08_1

J-GLOBAL

J-GLOBAL

記述言語：日本語   出版者・発行元：一般社団法人 日本機械学会  

Since powerful actuators are required for legged robots in practical use, it is considered that air cylinders, which have high power weight ratio, are suitable. In the report, we design a biped robot using air cylinders as actuators. For controlling air cylinders, it is difficult to apply them for mechanism of robots, since they have not enough precise positioning. Each air cylinder is attached to two links and imitates a bi-articular muscle. By the imitation, position definition precision is increased, even if the air cylinder is used as actuators. Moreover, air cylinders have damper function, and this function can be utilized for absorbing impact from a floor. This report shows these effectiveness by some inspections.

DOI： 10.1299/jsmermd.2014._1A1-Q03_1

J-GLOBAL

J-GLOBAL

記述言語：日本語   出版者・発行元：一般社団法人 日本ロボット学会  

In practical use of automatic guided vehicles, magnetic markers are widely used. However, an approach of which pattern of magnetic intensity in usual environment is defined as landmarks is not investigated. This reason is that it is difficult to be known environmental magnetic field since magnetic intensity is invisible. This paper shows investigation of environmental magnetic field in actual environment and describes implementation of the magnetic based navigation, magnetic navigation method. As the magnetic investigation, magnetic intensity of the mounted devices in a mobile robot was measured, and condition of efficient layout of the devices was obtained. By the measurement of environmental magnetic field in mentioned condition, pattern of magnetic intensity that is suitable as a landmark is shown in this paper. The mobile robot records magnetic intensity on its travel path as magnetic map, and achieves stable navigation based on the magnetic map. In this paper, performance of the magnetic navigation method is shown by an experiment.

DOI： 10.7210/jrsj.32.395

CiNii Books

J-GLOBAL

J-GLOBAL

記述言語：日本語   出版者・発行元：一般社団法人 日本機械学会  

Many studies on autonomous mobile robots field have been worked. However, mobile robots which work in actual environments are not developed yet. We have developed a personal mobility robot which supports persons in civil environment. The robot can also collect magnetic data during driving. It is permitted that we conduct experiments with use of the robot in Tsukuba Mobility Robot Special District. In the report, the specification of the robot is described. Moreover, the possibility is indicated that a constructed magnetic map by the robot can be shared by other robots. Finally, we discuss about the knowledge obtained by developing the robot.

DOI： 10.1299/jsmermd.2014._2A1-I02_1

J-GLOBAL

J-GLOBAL

記述言語：日本語   出版者・発行元：一般社団法人 日本機械学会  

This report describes performance of a guidance robot that leads persons in public space. The robot has a unique navigation system consisting of multiple agents as moving method. One of the moving methods is the magnetic navigation method, which was proposed by the authors, and mainly executed in the navigation system. The other methods are for supporting the magnetic navigation to induce the robot to the target path. Flexible and stable behavior is spontaneously generated by cooperation of processes of every method, which are independently executed. By the navigation system, a robot enables guidance navigation in the public space with pedestrians and bicycles. In ROBOMEC 2013, demonstration guiding participants to the venue will be planed, and it is assumed that many obstacles surrounding the robot. In this report, it is shown performance of the navigation system by experimental results that the robot accomplishes stable guiding navigation in the assumed situation.

DOI： 10.1299/jsmermd.2013._2P1-R07_1

J-GLOBAL

記述言語：日本語   出版者・発行元：一般社団法人 日本機械学会  

We have proposed a navigation method using magnetic information that occurs in the environment. This paper proposes a improve navigation method that combines a localization using magnetic information and a lateral error compensation based on external geometric information. In our previous method, it is required to adjust parameters used for the robot navigation. This adjustment is needed excluding unreliable magnetic information. On the other hand, our proposed method enables a robot to travel long distance without adjustment parameters even if the unreliable magnetic information is included. The robot is able to identify its position with the particle filter on a topological map using magnetic information. Furthermore, the robot uses external geometric information for only compensate the lateral error. As a result, the localization accuracy is increased and is not depend on geometric information. In addition, these methods are applicable to the robot using simple algorithm, computational and memory costs are low. Through the navigation experiments, we show that the robot achieved over 2 km navigation in real world. Moreover, the proposed method is compared to other two methods. Finally, the usefulness and advantage of the proposed method are presented.

DOI： 10.1299/kikaic.79.681

Scopus

J-GLOBAL

J-GLOBAL

記述言語：日本語   出版者・発行元：日本原子力研究開発機構  

CiNii Books

J-GLOBAL

記述言語：日本語   出版者・発行元：一般社団法人 日本機械学会  

Preliminary examination of image processing was conducted using existing reactor inside images through a fiber scope in order to confirm applicability of 3D-mapping in a reactor as a part of development of 3D-measurement technology. The Upright SURF (Speeded Up Robust Features) was used to find corresponding points between two captured images. In case of images showing many similar textures or lack of texture, it was difficult to find corresponding points using SURF only. By coupling with a canny algorithm to detect edges of the inside structure, it was found that 3-D structure could be measured for rectilinear objects.

DOI： 10.1299/jsmermd.2013._1P1-G07_1

J-GLOBAL

記述言語：日本語   出版者・発行元：一般社団法人 日本機械学会  

In order to entry the Special zone of experiment by mobility robots, it is required to obey the inspection of District Land Transport Bureaus in development of mobility robots. This report describes a challenge of development for a personal mobility robot that makes fun to ride. The mobility robot has two front driving and one rear free wheels, and the center of rider's body is placed on upper of the rear wheel. Therefore, the rider has fun since feels like rotating its body when the robot moves on curve. Furthermore, for fun, the shape of the robot is designed to be stylish since it is considered that its looks are important. As the results of developing the robot, this report shows the basic design for the inspection, assemble the chassis by using general parts, and molding the exterior body for stylish and safety.

DOI： 10.1299/jsmermd.2013._1P1-A06_1

J-GLOBAL

記述言語：日本語   出版者・発行元：一般社団法人 日本機械学会  

This paper describes a navigation method using environmental magnetic field called magnetic navigation based on topological map. The mobile robot that navigates with the magnetic navigation, estimates its position using change of environmental magnetic intensity. However, the magnetic navigation produces lateral error. Therefore, it is necessary to compensate that error. This paper proposes a method using Laser Scanner (LS) to compensate the lateral error occurred during the navigation. Since only two data of LS (one on the left and one on the right) are used in the proposed method, the mobile robot is able to navigate on a distance of 2km with a low computational cost in comparison to scan matching.

DOI： 10.1299/jsmermd.2012._1A2-I09_1

J-GLOBAL

J-GLOBAL

開催年月日： 2019年

開催年月日： 2019年

開催年月日： 2018年

開催年月日： 2018年

開催年月日： 2017年